Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/roomi-fields/paper-trailWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-audit-all)<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-audit-all"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-audit-all/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-audit-all"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-audit-all.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.00674 |
| Opus 5 | $0.00030 | $0.00337 |
| Sonnet 5 | $0.00012 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
paper-trail-audit-all scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/paper-trail:audit-all — Audit claims across the whole vault
Variante batch de /paper-trail:audit-sota. Parcourt toutes les SOTAs et
lance l'audit sur celles qui contiennent des refs non encore confirmées
au niveau du contenu.
Usage
/paper-trail:audit-all # toutes les SOTAs
/paper-trail:audit-all --sota-pattern "*tempo*" # filtre par nom de SOTA
/paper-trail:audit-all --dry-run # liste les SOTAs à auditer, ne lance rien
Ce que fait Claude
-
Lister les SOTAs du vault via l'adapter :
from adapters import get_adapter adapter = get_adapter() sotas = adapter.find_sotas() -
Pour chaque SOTA, identifier les refs citées (via wikilinks) et leur état FSM courant :
python3 -c " from adapters import get_adapter from pipeline.registry import load_ref from pipeline.config import REFS adapter = get_adapter() sota_path = ... for slug in adapter.parse_citations(sota_path): ref = load_ref(REFS / f'{slug}.md') if ref: print(f'{slug}: {ref.state}') " -
Filtrer : ne garder que les SOTAs qui ont au moins UNE ref en
page1_validated(= PDF acquis, page 1 validée techniquement, mais contenu pas encore audité contre les claims de la SOTA). -
Présenter à l'utilisateur :
- Tableau compact : nom SOTA, nombre total refs, nombre
page1_validatedà auditer, nombre déjàsota_cited_confirmed, nombreretracted. - Demander confirmation avant de lancer (l'audit peut prendre du temps car lit les PDFs).
- Tableau compact : nom SOTA, nombre total refs, nombre
-
Lancer audit-sota pour chaque SOTA filtrée. Utilise la skill
paper-trail:sota-auditor(déjà existante) ou directement la commande :/paper-trail:audit-sota <SOTA_path> -
Récap final :
- Par SOTA : nombre de refs validées (VRAI), corrigées (ADJUST), retractées (INVALID), non vérifiables (UNVERIFIABLE).
- Total cumulé.
Style
- Concis. Tableau markdown ≤ 120 caractères de large.
- Le batch peut être long → annoncer le temps estimé (≈ 2 min par SOTA).
- Permettre interruption : si l'utilisateur dit stop, sauvegarde la
progression dans
plans/audit_all_<date>.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 70 lines · 60 tokens per session scan A fa207ee8b1ee
paper-trail-audit-all is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 674 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
gh-security-review
Use to perform a dedicated security review of current branch changes before pushing.
gh-release
Create a new release for the marketplace or a specific plugin.
ledger-research
Launch parallel evidence collection across all active research pillars.
ledger-spec
Generate constrained PRD and architecture documents where every section cites decisions.
quick-research
Quick research with source verification (lighter than /deep-research).
gh-status
Quick overview of current GitHub workflow state.